Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, idempotent, non-destructive), it discloses that records are grouped by section, that record mode is paged by offset, that a count whose records no longer rebuild is refused rather than replaced, that there is no AI-credit charge, and that the output is untrusted customer-derived data that must not be treated as instructions. Those are genuine behavioral facts an agent cannot get from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The answer to 'why this number' is front-loaded and the whole description is three sentences with no filler. Some clauses (the count-refusal and credit notes) are packed into long sentences, but each one carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Annotations already cover the safety profile and an output schema exists, so the description does not need return-value detail; it correctly focuses on mode selection, paging, refusal behavior and trust cautions. The main remaining gap is how definition_id and run_id identify a published run.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden of explaining the parameters, and it does so for count_key, section_key, record_id and offset (paging). The two required parameters, definition_id and run_id, are only implied by 'published run' and never explained directly, which leaves a real gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource: retrieve the stored records behind one count of a published run, or a single record plus the messages it cites. The 'Why this number' framing tells an agent exactly what question this tool answers. It does not, however, differentiate itself from get_period_report or get_period_report_run, which an agent must infer from naming alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit branch conditions: pass count_key (optionally with section_key) to get the records behind a count, or pass record_id to get one record with its citations. That is clear mode selection. It stops short of saying when to pick this tool over the sibling report tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.